This review paper investigates how machine learning (ML) has transformed multiple facets of aviation engineering. The work demonstrates substantial progress in flight operations and air traffic management (ATM) optimization through frameworks such as Reinforcement-Learning-Informed Prescriptive Analytics (RLIPA) and deep reinforcement learning (DRL) techniques applied to conflict resolution. The study highlights how ML contributes to operational efficiency through faster computational processes and better decision-making abilities for those who control air traffic. The paper examines how leading firms such as SpaceX and Raytheon use ML technology to enhance manufacturing processes, including predictive maintenance (PdM) and autonomous systems development. The paper discusses ML implementation obstacles, including model interpretability, and highlights further research requirements for adapting to real-world issues such as changing traffic volumes and weather variations. Overall, the study demonstrates how ML technology can transform aviation engineering through enhancements in safety standards as well as operational and process efficiency.
A Review of Machine Learning Applications in Aviation Engineering
2025
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
TIBKAT | 1963(1963/64),1-3[?]
Service aviation, aeronautical engineering and commercial aviation
Engineering Index Backfile | 1927
|AUTOENCODING FEATURES FOR AVIATION MACHINE LEARNING PROBLEMS
TIBKAT | 2021
|